Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    significant extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    های
    3.32
    ত
    3.07
    jší
    3.03
    ۰
    3.01
    습니다
    2.90
    ان
    2.77
    an
    2.76
    𝐣
    2.65
    ться
    2.64
    कर
    2.55
    POSITIVE LOGITS
    𝗵
    2.66
    ि
    2.62
    𝗧
    2.44
     snowfall
    2.44
    ⟺
    2.42
     stenosis
    2.26
    dans
    2.18
     padam
    2.18
    𝗜
    2.11
    \|_{
    2.11
    Act Density 0.062%

    No Known Activations